AI agents call load_source to retrieve information from Graph Tool Call without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Without a description, confidence is reduced. The name 'load_source' most naturally suggests a read operation (loading/retrieving data from a source) rather than write, execute, or destructive actions. In the context of a graph-tool-call server that retrieves workflows and tool schemas, loading a source likely means fetching or querying configuration, schema, or graph data.
From the tool's definition Tool name 'load_source' suggests retrieving or loading data from a source, which aligns with Read operations (query, fetch, get). However, the description is empty, making it difficult to assess whether it retrieves data, modifies it, or executes operations.
Documented attack patterns abuse exactly the kind of access load_source gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Graph Tool Call, and nothing reaches the server without passing your rules. This is the rule we recommend for load_source:
{
"version": "1",
"default": "deny",
"tools": {
"load_source": {}
}
}load_source is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
load_source. It is categorised as a Read tool in the Graph Tool Call MCP Server, which means it retrieves data without modifying state.
Register the Graph Tool Call MCP server in PolicyLayer and add a rule for load_source: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Graph Tool Call. Nothing to install.
load_source is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the load_source rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for load_source. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
load_source is provided by the Graph Tool Call MCP server (sonaiengine/graph-tool-call). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Graph Tool Call, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
7 Graph Tool Call tools catalogued and risk-classified — across an index of 43,000+ MCP servers.